Despite recent progress, video generative models still struggle to generate delicate human actions (e.g., gymnastics), particularly when they are required to start from a user-provided reference image. In this paper, we explore the task of learning to animate images into videos that portray delicate human actions using a small number of videos — 16 or fewer — which reduces the need for extensive data collection and enhances practicality for real-world applications. Learning generalizable motion patterns that smoothly transition from user-provided reference images in such a few-shot setting is highly challenging. We propose FLASH (Few-shot Learning to Animate and Steer Humans), which enhances generalization of motion by training the model to reconstruct a video using the motion features and cross-frame correspondences extracted from another video with the same motion but different appearance. This encourages the learning of transferable motion and mitigates overfitting to the appearance in limited training data. Additionally, FLASH extends the decoder with additional layers to propagate details from the reference image to generated frames, improving transition smoothness. Human judges significantly favor FLASH, with 65.78% of 488 responses prefer FLASH over baselines. We strongly recommend watching the videos on the webpage1, as motion artifacts are hard to notice from images.

Paired image-text data with subtle variations in-between (e.g., people holding surfboards vs. people holding shovels) hold the promise of producing Vision-Language Models with proper compositional understanding. Synthesizing such training data from generative models is a highly coveted prize due to the reduced cost of data collection. However, synthesizing training images for compositional learning presents three challenges: (1) efficiency in generating large quantities of images, (2) text alignment between the generated image and the caption in the exact place of the subtle change, and (3) image fidelity in ensuring sufficient similarity with the original real images in all other places. We propose SPARCL (Synthetic Perturbations for Advancing Robust Compositional Learning), which integrates image feature injection into a fast text-to-image generative model, followed by an image style transfer step, to meet the three challenges. Further, to cope with any residual issues of text alignment, we propose an adaptive margin loss to filter out potentially incorrect synthetic samples and focus the learning on informative hard samples. Evaluation on four compositional understanding benchmarks demonstrates that SPARCL significantly improves the compositionality of CLIP, boosting the average accuracy of the CLIP base model by over 8% across all benchmarks and outperforming state-of-the-art methods by 2% on three benchmarks.

Scaling inference-time computation is increasingly seen as the next frontier in scaling laws for large language models. Previous work in mathematics and coding has demonstrated the remarkable potential for inference-time scaling. During such scaling, fine-grained supervision through process-based reward models (PRMs) is essential for enhancement. However, exploration of inference-time scaling and PRMs in open-domain problems remains limited, where lacking exact answers and obtaining process supervision prove challenging. In this paper, we explore the construction of PRMs for open-domain tasks, specifically for instruction-following tasks. Utilizing existing outcome-based reward models (ORMs), we develop sentence-level preference trees based on the prefix similarity of parallel sampled candidates from datasets like UltraFeedback. This setup allows us to derive weak supervision for processes via back-propagation from outcome-level rewards. Subsequently, we integrate ORMs and PRMs under the same pairwise ranking objectives, resulting in our newly developed reward models, named OpenPRM. This approach significantly enhances the scalability of process-level supervision in open domains at minimal cost. We assess the performance of OpenPRM across various reward benchmarks, demonstrating its competitive edge over traditional ORMs in open domains and PRMs in specialized domains. Additionally, we investigate the scalability of inference-time computation for open-domain instructions. Our results highlight the limitations of ORMs’ scalability, while OpenPRM shows superior performance in scaled settings. Despite these advances, achieving automatic fine-grained supervision for open-domain inference-time scaling remains a substantial challenge. We hope these findings will spur further development of process supervision reward models in open-domain scenarios.

Micro-expressions (MEs) are spontaneous facial movements that reveal an individual’s genuine emotions and play a crucial role in various domains, including lie detection, criminal analysis, mental health treatment, national security, and others. Micro-expression recognition is a highly complex aspect within the domain of affective computing, aimed at identifying subtle facial motions that are difficult for humans to discern accurately. To model the subtle facial muscle motions and the brief duration of MEs, we propose a robust micro-expression recognition (MER) network, named the attention mechanism-based motion magnification guided micro-expression recognition network (AM-MM-MER). This network consists of two primary components: the ST-MEMM network, which enhances subtle motions in micro-expression videos to reveal imperceptible facial muscle motions, and the AM-MER, which focuses on facial landmarks related to micro-expressions and incorporates novel landmark positions to extract the underlying relationships among these landmarks, thereby reducing interference from video magnification and irrelevant identity features. Extensive analysis on the CASME II and SAMM datasets demonstrates the high accuracy and effectiveness of the proposed network, achieving superior results compared to state-of-the-art methods. Ablation studies further illustrate the robustness of the proposed network.

Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains and are moving towards more specialized areas. Recent advanced proprietary models such as GPT-4 and Gemini have achieved significant advancements in biomedicine, which have also raised privacy and security challenges. The construction of specialized generalists hinges largely on high-quality datasets, enhanced by techniques like supervised fine-tuning and reinforcement learning from human or AI feedback, and direct preference optimization. However, these leading technologies (e.g., preference learning) are still significantly limited in the open source community due to the scarcity of specialized data. In this paper, we present the UltraMedical collections, which consist of high-quality manual and synthetic datasets in the biomedicine domain, featuring preference annotations across multiple advanced LLMs. By utilizing these datasets, we fine-tune a suite of specialized medical models based on Llama-3 series, demonstrating breathtaking capabilities across various medical benchmarks. Moreover, we develop powerful reward models skilled in biomedical and general reward benchmark, enhancing further online preference learning within the biomedical LLM community.

In video action recognition, shortcut static features can interfere with the learning of motion features, resulting in poor out-of-distribution (OOD) generalization. The video background is clearly a source of static bias, but the video foreground, such as the clothing of the actor, can also provide static bias. In this paper, we empirically verify the existence of foreground static bias by creating test videos with conflicting signals from the static and moving portions of the video. To tackle this issue, we propose a simple yet effective technique, StillMix, to learn robust action representations. Specifically, StillMix identifies bias-inducing video frames using a 2D reference network and mixes them with videos for training, serving as effective bias suppression even when we cannot explicitly extract the source of bias within each video frame or enumerate types of bias. Finally, to precisely evaluate static bias, we synthesize two new benchmarks, SCUBA for static cues in the background, and SCUFO for static cues in the foreground. With extensive experiments, we demonstrate that StillMix mitigates both types of static bias and improves video representations for downstream applications. Code is available at https://github.com/lihaoxin05/StillMix.

Egocentric videos, which record the daily activities of individuals from a first-person point of view, have attracted increasing attention during recent years because of their growing use in many popular applications, including life logging, health monitoring and virtual reality. As a fundamental problem in egocentric vision, one of the tasks of egocentric action recognition aims to recognize the actions of the camera wearers from egocentric videos. In egocentric action recognition, relation modeling is important, because the interactions between the camera wearer and the recorded persons or objects form complex relations in egocentric videos. However, only a few of existing methods model the relations between the camera wearer and the interacting persons for egocentric action recognition, and moreover they require prior knowledge or auxiliary data to localize the interacting persons. In this work, we consider modeling the relations in a weakly supervised manner, i.e., without using annotations or prior knowledge about the interacting persons or objects, for egocentric action recognition. We form a weakly supervised framework by unifying automatic interactor localization and explicit relation modeling for the purpose of automatic relation modeling. First, we learn to automatically localize the interactors, i.e., the body parts of the camera wearer and the persons or objects that the camera wearer interacts with, by learning a series of keypoints directly from video data to localize the action-relevant regions with only action labels and some constraints on these keypoints. Second, more importantly, to explicitly model the relations between the interactors, we develop an ego-relational LSTM (long short-term memory) network with several candidate connections to model the complex relations in egocentric videos, such as the temporal, interactive, and contextual relations. In particular, to reduce human efforts and manual interventions needed to construct an optimal ego-relational LSTM structure, we search for the optimal connections by employing a differentiable network architecture search mechanism, which automatically constructs the ego-relational LSTM network to explicitly model different relations for egocentric action recognition. We conduct extensive experiments on egocentric video datasets to illustrate the effectiveness of our method.

Long-term actions involve many important visual concepts, e.g., objects, motions, and sub-actions, and there are various relations among these concepts, which we call basic relations. These basic relations will jointly affect each other during the temporal evolution of long-term actions, which forms the high-order relations that are essential for long-term action recognition. In this paper, we propose a Graph-based High-order Relation Modeling (GHRM) module to exploit the high-order relations in the long-term actions for long-term action recognition. In GHRM, each basic relation in the long-term actions will be modeled by a graph, where each node represents a segment in a long video. Moreover, when modeling each basic relation, the information from all the other basic relations will be incorporated by GHRM, and thus the high-order relations in the long-term actions can be well exploited. To better exploit the high-order relations along the time dimension, we design a GHRM-layer consisting of a Temporal-GHRM branch and a Semantic-GHRM branch, which aims to model the local temporal high-order relations and global semantic high-order relations. The experimental results on three long-term action recognition datasets, namely, Breakfast, Charades, and MultiThumos, demonstrate the effectiveness of our model.

Interaction modeling is important for video action analysis. Recently, several works design specific structures to model interactions in videos. However, their structures are manually designed and non-adaptive, which require structures design efforts and more importantly could not model interactions adaptively. In this paper, we automate the process of structures design to learn adaptive structures for interaction modeling. We propose to search the network structures with differentiable architecture search mechanism, which learns to construct adaptive structures for different videos to facilitate adaptive interaction modeling. To this end, we first design the search space with several basic graph operations that explicitly capture different relations in videos. We experimentally demonstrate that our architecture search framework learns to construct adaptive interaction modeling structures, which provides more understanding about the relations between the structures and some interaction characteristics, and also releases the requirement of structures design efforts. Additionally, we show that the designed basic graph operations in the search space are able to model different interactions in videos. The experiments on two interaction datasets show that our method achieves competitive performance with state-of-the-arts.

Predicting action class from partially observed videos, which is known as action prediction, is an important task in computer vision field with many applications. The challenge for action prediction mainly lies in the lack of discriminative action information for the partially observed videos. To tackle this challenge, in this work, we propose to transfer action knowledge learned from fully observed videos for improving the prediction of partially observed videos. Specifically, we develop a two-stage learning framework for action knowledge transfer. At the first stage, we learn feature embeddings and discriminative action classifier from full videos. The knowledge in the learned embeddings and classifier is then transferred to the partial videos at the second stage. Our experiments on the UCF-101 and HMDB-51 datasets show that the proposed action knowledge transfer method can significantly improve the performance of action prediction, especially for the actions with small observation ratios (e.g., 10%). We also experimentally illustrate that our method outperforms all the state-of-the-art action prediction systems.

Egocentric interaction recognition aims to recognize the camera wearer's interactions with the interactor who faces the camera wearer in egocentric videos. In such a human-human interaction analysis problem, it is crucial to explore the relations between the camera wearer and the interactor. However, most existing works directly model the interactions as a whole and lack modeling the relations between the two interacting persons. To exploit the strong relations for egocentric interaction recognition, we introduce a dual relation modeling framework which learns to model the relations between the camera wearer and the interactor based on the individual action representations of the two persons. Specifically, we develop a novel interactive LSTM module, the key component of our framework, to explicitly model the relations between the two interacting persons based on their individual action representations, which are collaboratively learned with an interactor attention module and a global-local motion module. Experimental results on three egocentric interaction datasets show the effectiveness of our method and advantage over state-of-the-arts.

Most of current Convolution Neural Network (CNN) based methods for optical flow estimation focus on learning optical flow on synthetic datasets with groundtruth, which is not practical. In this paper, we propose an unsupervised optical flow estimation framework named PCLNet. It uses pyramid Convolution LSTM (ConvLSTM) with the constraint of adjacent frame reconstruction, which allows flexibly estimating multi-frame optical flows from any video clip. Besides, by decoupling motion feature learning and optical flow representation, our method avoids complex short-cut connections used in existing frameworks while improving accuracy of optical flow estimation. Moreover, different from those methods using specialized CNN architectures for capturing motion, our framework directly learns optical flow from the features of generic CNNs and thus can be easily embedded in any CNN based frameworks for other tasks. Extensive experiments have verified that our method not only estimates optical flow effectively and accurately, but also obtains comparable performance on action recognition.